© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 11388
    Prev
    Next
    INDEX
    Explanations

    phrases related to contractual agreements and trade deals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    320
    +0.15
    0.8%
    73
    +0.13
    0.7%
    237
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.15
    0.11
    8
    +0.13
    0.04
    73
    +0.11
    0.05
    Negative Logits
    ĻĤ
    -3.69
    Ĵ
    -3.24
    ¿½
    -3.09
    ¿
    -3.05
    ¾
    -3.04
    Ł
    -3.00
    Ļª
    -2.95
    ´
    -2.92
    ľĵ
    -2.89
    ³
    -2.88
    POSITIVE LOGITS
     negotiations
    2.27
     negotiation
    2.14
     negotiated
    2.13
     deadline
    2.10
     2021
    2.06
     treaty
    2.04
     expires
    2.04
     bipartisan
    2.03
     unanimous
    1.98
     arbitration
    1.94
    Activations Density 3.690%

    No Known Activations